Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    avia
    -0.78
    erk
    -0.76
    stead
    -0.73
    uron
    -0.73
    alon
    -0.73
    ufact
    -0.72
    assador
    -0.72
    yip
    -0.68
    imore
    -0.67
    iversity
    -0.65
    POSITIVE LOGITS
     è£ıè
    0.73
    ãĤ£
    0.72
    çīĪ
    0.66
    fitting
    0.64
     Freak
    0.64
     Poker
    0.63
    natureconservancy
    0.62
     Revelations
    0.62
     Twist
    0.62
     Kuro
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.